[binutils-gdb] Fix setting-breakpoints regression on PPC64 (function descriptors)

[Pedro Alves <palves at sourceware dot org>]

https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=4024cf2b8d864279ff87af1a2ade77ab6d710d50

commit 4024cf2b8d864279ff87af1a2ade77ab6d710d50
Author: Pedro Alves <palves@redhat.com>
Date:   Wed Nov 29 19:25:58 2017 +0000

    Fix setting-breakpoints regression on PPC64 (function descriptors)
    
    The recent-ish commit e5f25bc5d6db ('Fix "list ambiguous_variable"')
    caused a serious regression on PPC64.  See
    <https://sourceware.org/ml/gdb-patches/2017-11/msg00666.html>.
    
    Basically, after that patch, GDB sets breakpoints in function
    descriptors instead of where the descriptors point to, which is
    incorrect.
    
    The problem is that GDB now only runs a minsym's address through
    gdbarch_convert_from_func_ptr_addr if msymbol_is_text returns true.
    However, if the symbol points to a function descriptor,
    msymbol_is_text is false since function descriptors are in fact
    outside the text section.
    
    The fix is to also run a non-text address through
    gdbarch_convert_from_func_ptr_addr, and if that detects that it was
    indeed a function descriptor, treat the resulting address as a
    function.
    
    While implementing that directly in linespec.c:minsym_found (where the
    bad msymbol_is_text check is) fixes the issue, I noticed that
    linespec.c:add_minsym has some code that also basically needs to do
    the same checks, however it's implemented differently.  Also,
    add_minsym is calling find_pc_sect_line on non-function symbols, which
    also doesn't look right.
    
    So I introduced msymbol_is_function, so that we have a simple place to
    consider minsyms and function descriptors.
    
    And then, the only other use of msymbol_is_text is in
    find_function_alias_target, which turns out to also be incorrect.
    Changing that one to use msymbol_is_function, i.e., to consider
    function descriptors too fixes (on PPC64):
    
      -FAIL: gdb.base/symbol-alias.exp: p func_alias
      -FAIL: gdb.base/symbol-alias.exp: p *func_alias()
      +PASS: gdb.base/symbol-alias.exp: p func_alias
      +PASS: gdb.base/symbol-alias.exp: p *func_alias()
    
    And then after that, msymbol_is_text is no longer used anywhere, so it
    can be removed.
    
    Tested on x86_64 GNU/Linux, no regressions.  Tested on PPC64 GNU/Linux
    and results compared to a testrun of e5f25bc5d6db^ (before the
    offending commit), also no regressions.  (there's a couple new FAILs
    and some new symbol name matching unit tests are crashing, but that
    looks unrelated).
    
    gdb/ChangeLog:
    2017-11-29  Pedro Alves  <palves@redhat.com>
    
    	* linespec.c (minsym_found, add_minsym): Use msymbol_is_function.
    	* minsyms.c (msymbol_is_text): Delete.
    	(msymbol_is_function): New function.
    	* minsyms.h (msymbol_is_text): Delete.
    	(msymbol_is_function): New declaration.
    	* symtab.c (find_function_alias_target): Use msymbol_is_function.

Diff:
---
 gdb/ChangeLog  |  9 +++++++
 gdb/linespec.c | 79 ++++++++++++++--------------------------------------------
 gdb/minsyms.c  | 34 +++++++++++++++++++------
 gdb/minsyms.h  | 11 +++++---
 gdb/symtab.c   |  8 +++---
 5 files changed, 66 insertions(+), 75 deletions(-)

diff --git a/gdb/ChangeLog b/gdb/ChangeLog
index bd1eccf..c8f8e26 100644
--- a/gdb/ChangeLog
+++ b/gdb/ChangeLog
@@ -1,3 +1,12 @@
+2017-11-29  Pedro Alves  <palves@redhat.com>
+
+	* linespec.c (minsym_found, add_minsym): Use msymbol_is_function.
+	* minsyms.c (msymbol_is_text): Delete.
+	(msymbol_is_function): New function.
+	* minsyms.h (msymbol_is_text): Delete.
+	(msymbol_is_function): New declaration.
+	* symtab.c (find_function_alias_target): Use msymbol_is_function.
+
 2017-11-29  Tom Tromey  <tom@tromey.com>
 
 	* Makefile.in (distclean): Handle the case where rmdir fails.
diff --git a/gdb/linespec.c b/gdb/linespec.c
index 3f7f171..f1e1ea9 100644
--- a/gdb/linespec.c
+++ b/gdb/linespec.c
@@ -4309,22 +4309,12 @@ minsym_found (struct linespec_state *self, struct objfile *objfile,
 	      struct minimal_symbol *msymbol,
 	      std::vector<symtab_and_line> *result)
 {
-  struct gdbarch *gdbarch = get_objfile_arch (objfile);
-  CORE_ADDR pc;
   struct symtab_and_line sal;
 
-  if (msymbol_is_text (msymbol))
+  CORE_ADDR func_addr;
+  if (msymbol_is_function (objfile, msymbol, &func_addr))
     {
-      sal = find_pc_sect_line (MSYMBOL_VALUE_ADDRESS (objfile, msymbol),
-			       (struct obj_section *) 0, 0);
-      sal.section = MSYMBOL_OBJ_SECTION (objfile, msymbol);
-
-      /* The minimal symbol might point to a function descriptor;
-	 resolve it to the actual code address instead.  */
-      pc = gdbarch_convert_from_func_ptr_addr (gdbarch, sal.pc,
-					       &current_target);
-      if (pc != sal.pc)
-	sal = find_pc_sect_line (pc, NULL, 0);
+      sal = find_pc_sect_line (func_addr, NULL, 0);
 
       if (self->funfirstline)
 	{
@@ -4332,14 +4322,9 @@ minsym_found (struct linespec_state *self, struct objfile *objfile,
 	      && (COMPUNIT_LOCATIONS_VALID (SYMTAB_COMPUNIT (sal.symtab))
 		  || SYMTAB_LANGUAGE (sal.symtab) == language_asm))
 	    {
-	      /* If gdbarch_convert_from_func_ptr_addr does not apply then
-		 sal.SECTION, sal.LINE&co. will stay correct from above.
-		 If gdbarch_convert_from_func_ptr_addr applies then
-		 sal.SECTION is cleared from above and sal.LINE&co. will
-		 stay correct from the last find_pc_sect_line above.  */
-	      sal.pc = MSYMBOL_VALUE_ADDRESS (objfile, msymbol);
-	      sal.pc = gdbarch_convert_from_func_ptr_addr (gdbarch, sal.pc,
-							   &current_target);
+	      struct gdbarch *gdbarch = get_objfile_arch (objfile);
+
+	      sal.pc = func_addr;
 	      if (gdbarch_skip_entrypoint_p (gdbarch))
 		sal.pc = gdbarch_skip_entrypoint (gdbarch, sal.pc);
 	    }
@@ -4424,52 +4409,26 @@ static void
 add_minsym (struct minimal_symbol *minsym, void *d)
 {
   struct collect_minsyms *info = (struct collect_minsyms *) d;
-  bound_minimal_symbol_d mo;
-
-  mo.minsym = minsym;
-  mo.objfile = info->objfile;
 
   if (info->symtab != NULL)
     {
-      CORE_ADDR pc;
-      struct symtab_and_line sal;
-      struct gdbarch *gdbarch = get_objfile_arch (info->objfile);
-
-      sal = find_pc_sect_line (MSYMBOL_VALUE_ADDRESS (info->objfile, minsym),
-			       NULL, 0);
-      sal.section = MSYMBOL_OBJ_SECTION (info->objfile, minsym);
-      pc
-	= gdbarch_convert_from_func_ptr_addr (gdbarch, sal.pc, &current_target);
-      if (pc != sal.pc)
-	sal = find_pc_sect_line (pc, NULL, 0);
+      /* We're looking for a label for which we don't have debug
+	 info.  */
+      CORE_ADDR func_addr;
+      if (msymbol_is_function (info->objfile, minsym, &func_addr))
+	{
+	  symtab_and_line sal = find_pc_sect_line (func_addr, NULL, 0);
 
-      if (info->symtab != sal.symtab)
-	return;
+	  if (info->symtab != sal.symtab)
+	    return;
+	}
     }
 
-  /* Exclude data symbols when looking for breakpoint locations.   */
-  if (!info->list_mode)
-    switch (minsym->type)
-      {
-	case mst_slot_got_plt:
-	case mst_data:
-	case mst_bss:
-	case mst_abs:
-	case mst_file_data:
-	case mst_file_bss:
-	  {
-	    /* Make sure this minsym is not a function descriptor
-	       before we decide to discard it.  */
-	    struct gdbarch *gdbarch = get_objfile_arch (info->objfile);
-	    CORE_ADDR addr = gdbarch_convert_from_func_ptr_addr
-			       (gdbarch, BMSYMBOL_VALUE_ADDRESS (mo),
-				&current_target);
-
-	    if (addr == BMSYMBOL_VALUE_ADDRESS (mo))
-	      return;
-	  }
-      }
+  /* Exclude data symbols when looking for breakpoint locations.  */
+  if (!info->list_mode && !msymbol_is_function (info->objfile, minsym))
+    return;
 
+  bound_minimal_symbol_d mo = {minsym, info->objfile};
   VEC_safe_push (bound_minimal_symbol_d, info->msyms, &mo);
 }
 
diff --git a/gdb/minsyms.c b/gdb/minsyms.c
index 4898da1..d68fb65 100644
--- a/gdb/minsyms.c
+++ b/gdb/minsyms.c
@@ -57,17 +57,35 @@
 /* See minsyms.h.  */
 
 bool
-msymbol_is_text (minimal_symbol *msymbol)
+msymbol_is_function (struct objfile *objfile, minimal_symbol *minsym,
+		     CORE_ADDR *func_address_p)
 {
-  switch (MSYMBOL_TYPE (msymbol))
+  CORE_ADDR msym_addr = MSYMBOL_VALUE_ADDRESS (objfile, minsym);
+
+  switch (minsym->type)
     {
-    case mst_text:
-    case mst_text_gnu_ifunc:
-    case mst_solib_trampoline:
-    case mst_file_text:
-      return true;
+    case mst_slot_got_plt:
+    case mst_data:
+    case mst_bss:
+    case mst_abs:
+    case mst_file_data:
+    case mst_file_bss:
+      {
+	struct gdbarch *gdbarch = get_objfile_arch (objfile);
+	CORE_ADDR pc = gdbarch_convert_from_func_ptr_addr (gdbarch, msym_addr,
+							   &current_target);
+	if (pc != msym_addr)
+	  {
+	    if (func_address_p != NULL)
+	      *func_address_p = pc;
+	    return true;
+	  }
+	return false;
+      }
     default:
-      return false;
+      if (func_address_p != NULL)
+	*func_address_p = msym_addr;
+      return true;
     }
 }
 
diff --git a/gdb/minsyms.h b/gdb/minsyms.h
index 5c0dde4..baa87f0 100644
--- a/gdb/minsyms.h
+++ b/gdb/minsyms.h
@@ -159,9 +159,14 @@ void terminate_minimal_symbol_table (struct objfile *objfile);
 
 
 
-/* Return whether MSYMBOL is a function/method.  */
-
-bool msymbol_is_text (minimal_symbol *msymbol);
+/* Return whether MSYMBOL is a function/method.  If FUNC_ADDRESS_P is
+   non-NULL, and the MSYMBOL is a function, then *FUNC_ADDRESS_P is
+   set to the function's address, already resolved if MINSYM points to
+   a function descriptor.  */
+
+bool msymbol_is_function (struct objfile *objfile,
+			  minimal_symbol *minsym,
+			  CORE_ADDR *func_address_p = NULL);
 
 /* Compute a hash code for the string argument.  */
 
diff --git a/gdb/symtab.c b/gdb/symtab.c
index 3d59367..a249a8d 100644
--- a/gdb/symtab.c
+++ b/gdb/symtab.c
@@ -3927,14 +3927,14 @@ skip_prologue_using_sal (struct gdbarch *gdbarch, CORE_ADDR func_addr)
 symbol *
 find_function_alias_target (bound_minimal_symbol msymbol)
 {
-  if (!msymbol_is_text (msymbol.minsym))
+  CORE_ADDR func_addr;
+  if (!msymbol_is_function (msymbol.objfile, msymbol.minsym, &func_addr))
     return NULL;
 
-  CORE_ADDR addr = BMSYMBOL_VALUE_ADDRESS (msymbol);
-  symbol *sym = find_pc_function (addr);
+  symbol *sym = find_pc_function (func_addr);
   if (sym != NULL
       && SYMBOL_CLASS (sym) == LOC_BLOCK
-      && BLOCK_START (SYMBOL_BLOCK_VALUE (sym)) == addr)
+      && BLOCK_START (SYMBOL_BLOCK_VALUE (sym)) == func_addr)
     return sym;
 
   return NULL;